Tomoyuki Kaneko

According to our database, Tomoyuki Kaneko authored at least 50 papers between 2000 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2024

Initial state diversification for efficient AlphaZero-style training.

Yosuke Demura, Tomoyuki Kaneko

J. Int. Comput. Games Assoc., 2024

2023

Curiosity-driven Exploration for Cooperative Multi-Agent Reinforcement Learning.

Fanchao Xu, Tomoyuki Kaneko

Proceedings of the International Joint Conference on Neural Networks, 2023

DEIR: Efficient and Robust Exploration through Discriminative-Model-Based Episodic Intrinsic Rewards.

Shanchuan Wan, Yujin Tang, Yingtao Tian, Tomoyuki Kaneko

Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, 2023

2022

Learning Strategies for Imperfect Information Board Games Using Depth-Limited Counterfactual Regret Minimization and Belief State.

Chen Chen, Tomoyuki Kaneko

Proceedings of the IEEE Conference on Games, CoG 2022, Beijing, 2022

2021

Residual Network for Deep Reinforcement Learning with Attention Mechanism.

Hanhua Zhu, Tomoyuki Kaneko

J. Inf. Sci. Eng., 2021

Local Coordination in Multi-Agent Reinforcement Learning.

Fanchao Xu, Tomoyuki Kaneko

Proceedings of the 2021 International Conference on Technologies and Applications of Artificial Intelligence, 2021

Maximum Entropy Reinforcement Learning in Two-Player Perfect Information Games.

Taichi Nakayashiki, Tomoyuki Kaneko

Proceedings of the IEEE Symposium Series on Computational Intelligence, 2021

Hierarchical Advantage for Reinforcement Learning in Parameterized Action Space.

Zhejie Hu, Tomoyuki Kaneko

Proceedings of the 2021 IEEE Conference on Games (CoG), 2021

Improving Counterfactual Regret Minimization Agents Training in Card Game Cheat Using Ordered Abstraction.

Cheng Yi, Tomoyuki Kaneko

Proceedings of the Advances in Computer Games - 17th International Conference, 2021

2020

Diverse Exploration via InfoMax Options.

Yuji Kanagawa, Tomoyuki Kaneko

CoRR, 2020

Evaluation of Loss Function for Stable Policy Learning in Dobutsu Shogi.

Taichi Nakayashiki, Tomoyuki Kaneko

Proceedings of the International Conference on Technologies and Applications of Artificial Intelligence, 2020

Playing Catan with Cross-Dimensional Neural Network.

Quentin Gendre, Tomoyuki Kaneko

Proceedings of the Neural Information Processing - 27th International Conference, 2020

2019

Computer Shogi Tournaments and Techniques.

Tomoyuki Kaneko, Takenobu Takizawa

IEEE Trans. Games, 2019

RankNet for evaluation functions of the game of Go.

Yusaku Mandai, Tomoyuki Kaneko

J. Int. Comput. Games Assoc., 2019

Deep Residual Attention Reinforcement Learning.

Hanhua Zhu, Tomoyuki Kaneko

Proceedings of the 2019 International Conference on Technologies and Applications of Artificial Intelligence, 2019

Application of Deep-RL with Sample-Efficient Method in Mini-games of StarCraft II.

Zhejie Hu, Tomoyuki Kaneko

Proceedings of the 2019 International Conference on Technologies and Applications of Artificial Intelligence, 2019

Acquiring Strategies for the Board Game Geister by Regret Minimization.

Chen Chen, Tomoyuki Kaneko

Proceedings of the 2019 International Conference on Technologies and Applications of Artificial Intelligence, 2019

Rogue-Gym: A New Challenge for Generalization in Reinforcement Learning.

Yuji Kanagawa, Tomoyuki Kaneko

Proceedings of the IEEE Conference on Games, 2019

2018

Comparison of Loss Functions for Training of Deep Neural Networks in Shogi.

Hanhua Zhu, Tomoyuki Kaneko

Proceedings of the Conference on Technologies and Applications of Artificial Intelligence, 2018

Application of Deep Reinforcement Learning in Werewolf Game Agents.

Tianhe Wang, Tomoyuki Kaneko

Proceedings of the Conference on Technologies and Applications of Artificial Intelligence, 2018

Deep Recurrent Q-Network with Truncated History.

Hyunwoo Oh, Tomoyuki Kaneko

Proceedings of the Conference on Technologies and Applications of Artificial Intelligence, 2018

Learning of Evaluation Functions via Self-Play Enhanced by Checkmate Search.

Taichi Nakayashiki, Tomoyuki Kaneko

Proceedings of the Conference on Technologies and Applications of Artificial Intelligence, 2018

Alternative Multitask Training for Evaluation Functions in Game of Go.

Yusaku Mandai, Tomoyuki Kaneko

Proceedings of the Conference on Technologies and Applications of Artificial Intelligence, 2018

Heterogeneous Multi-task Learning of Evaluation Functions for Chess and Shogi.

Shanchuan Wan, Tomoyuki Kaneko

Proceedings of the Neural Information Processing - 25th International Conference, 2018

Building Evaluation Functions for Chess and Shogi with Uniformity Regularization Networks.

Shanchuan Wan, Tomoyuki Kaneko

Proceedings of the 2018 IEEE Conference on Computational Intelligence and Games, 2018

2017

Imitation Learning for Playing Shogi Based on Generative Adversarial Networks.

Shanchuan Wan, Tomoyuki Kaneko

Proceedings of the Conference on Technologies and Applications of Artificial Intelligence, 2017

Estimating the Maximum Expected Value through Upper Confidence Bound of Likelihood.

Takahisa Imagawa, Tomoyuki Kaneko

Proceedings of the Conference on Technologies and Applications of Artificial Intelligence, 2017

2016

LinUCB applied to Monte Carlo tree search.

Yusaku Mandai, Tomoyuki Kaneko

Theor. Comput. Sci., 2016

Learning of Evaluation Functions to Realize Playing Styles in Shogi.

Shotaro Omori, Tomoyuki Kaneko

Proceedings of the PRICAI 2016: Trends in Artificial Intelligence, 2016

Improved LinUCT and its evaluation on incremental random-feature tree.

Yusaku Mandai, Tomoyuki Kaneko

Proceedings of the IEEE Conference on Computational Intelligence and Games, 2016

Monte Carlo Tree Search with Robust Exploration.

Takahisa Imagawa, Tomoyuki Kaneko

Proceedings of the Computers and Games - 9th International Conference, 2016

2015

Enhancements in Monte Carlo tree search algorithms for biased game trees.

Takahisa Imagawa, Tomoyuki Kaneko

Proceedings of the 2015 IEEE Conference on Computational Intelligence and Games, 2015

Estimating Ratings of Computer Players by the Evaluation Scores and Principal Variations in Shogi.

Shogo Takeuchi, Tomoyuki Kaneko

Proceedings of the 3rd International Conference on Applied Computing and Information Technology, 2015

Parameter-Free Tree Style Pipeline in Asynchronous Parallel Game-Tree Search.

Shu Yokoyama, Tomoyuki Kaneko, Tetsuro Tanaka

Proceedings of the Advances in Computer Games - 14th International Conference, 2015

2014

Large-Scale Optimization for Evaluation Functions with Minimax Search.

Kunihito Hoki, Tomoyuki Kaneko

J. Artif. Intell. Res., 2014

2013

Parallel Dovetailing and its Application to Depth-First Proof-Number Search.

Kunihito Hoki, Tomoyuki Kaneko, Akihiro Kishimoto, Takeshi Ito

J. Int. Comput. Games Assoc., 2013

Exploring the implicit interlayer regulatory mechanism between cells and tissue: Stochastic mathematical analyses of the spontaneous ordering in beating synchronization.

Hiroyuki Hamada, Fumimasa Nomura, Tomoyuki Kaneko, Kenji Yasuda, Masahiro Okamoto

Biosyst., 2013

A System-Design Outline of the Distributed-Shogi-System Akara 2010.

Kunihito Hoki, Tomoyuki Kaneko, Daisaku Yokoyama, Takuya Obata, Hiroshi Yamashita, Yoshimasa Tsuruoka, Takeshi Ito

Proceedings of the 14th ACIS International Conference on Software Engineering, 2013

2011

Scalable Distributed Monte-Carlo Tree Search.

Kazuki Yoshizoe, Akihiro Kishimoto, Tomoyuki Kaneko, Haruhiro Yoshimoto, Yutaka Ishikawa

Proceedings of the Fourth Annual Symposium on Combinatorial Search, 2011

Infinite Connect-Four Is Solved: Draw.

Yoshiaki Yamaguchi, Kazunori Yamaguchi, Tetsuro Tanaka, Tomoyuki Kaneko

Proceedings of the Advances in Computer Games - 13th International Conference, 2011

Analysis of Evaluation-Function Learning by Comparison of Sibling Nodes.

Tomoyuki Kaneko, Kunihito Hoki

Proceedings of the Advances in Computer Games - 13th International Conference, 2011

The Global Landscape of Objective Functions for the Optimization of Shogi Piece Values with a Game-Tree Search.

Kunihito Hoki, Tomoyuki Kaneko

Proceedings of the Advances in Computer Games - 13th International Conference, 2011

2010

Evaluation of Game Tree Search Methods by Game Records.

Shogo Takeuchi, Tomoyuki Kaneko, Kazunori Yamaguchi

IEEE Trans. Comput. Intell. AI Games, 2010

Parallel Depth First Proof Number Search.

Tomoyuki Kaneko

Proceedings of the Twenty-Fourth AAAI Conference on Artificial Intelligence, 2010

2008

Evaluation of Monte Carlo tree search and the application to Go.

Shogo Takeuchi, Tomoyuki Kaneko, Kazunori Yamaguchi

Proceedings of the 2008 IEEE Symposium on Computational Intelligence and Games, 2008

2007

Visualization and Adjustment of Evaluation Functions Based on Evaluation Values and Win Probability.

Shogo Takeuchi, Tomoyuki Kaneko, Kazunori Yamaguchi, Satoru Kawai

Proceedings of the Twenty-Second AAAI Conference on Artificial Intelligence, 2007

2006

Dual Lambda Search and Shogi Endgames.

Shunsuke Soeda, Tomoyuki Kaneko, Tetsuro Tanaka

Proceedings of the Advances in Computer Games, 11th International Conference, 2006

Monte Carlo Go Has a Way to Go.

Haruhiro Yoshimoto, Kazuki Yoshizoe, Tomoyuki Kaneko, Akihiro Kishimoto, Kenjiro Taura

Proceedings of the Proceedings, 2006

2003

Automated Identification of Patterns in Evaluation Functions.

Tomoyuki Kaneko, Kazunori Yamaguchi, Satoru Kawai

Proceedings of the Advances in Computer Games, 2003

2000

Compiling Logical Features into Specialized State-Evaluators by Partial Evaluation, Boolean Tables and Incremental Calculation.

Tomoyuki Kaneko, Kazunori Yamaguchi, Satoru Kawai

Proceedings of the PRICAI 2000, Topics in Artificial Intelligence, 6th Pacific Rim International Conference on Artificial Intelligence, Melbourne, Australia, August 28, 2000